[VPlan] Compute cost single-scalar calls in computeCost. (NFC)

Compute the cost of non-intrinsic, single-scalar calls directly in
VPReplicateRecipe::computeCost.

This starts moving call cost computations to VPlan, handling the
simplest case first.

(Cherry-picked from 79be94c)

Author: fhahn

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -2947,6 +2947,24 @@ InstructionCost VPReplicateRecipe::computeCost(ElementCount VF,
     // is scalarized or not. Therefore, we handle GEPs with the memory
     // instruction cost.
     return 0;
+  case Instruction::Call: {
+    if (!isSingleScalar()) {
+      // TODO: Handle remaining call costs here as well.
+      if (VF.isScalable())
+        return InstructionCost::getInvalid();
+      break;
+    }
+
+    auto *CalledFn =
+        cast<Function>(getOperand(getNumOperands() - 1)->getLiveInIRValue());
+    if (CalledFn->isIntrinsic())
+      break;
+
+    SmallVector<Type *, 4> Tys;
+    for (VPValue *ArgOp : drop_end(operands()))
+      Tys.push_back(Ctx.Types.inferScalarType(ArgOp));
+    return Ctx.TTI.getCallInstrCost(CalledFn, ResultTy, Tys, Ctx.CostKind);
+  }
   case Instruction::Add:
   case Instruction::Sub:
   case Instruction::FAdd: